© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50972
    Prev
    Next
    INDEX
    Explanations

    mm, inch, units, measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Serving
    -0.12
    inea
    -0.11
     Bloody
    -0.11
     crawling
    -0.10
     scram
    -0.09
     stall
    -0.09
    uta
    -0.09
     saddle
    -0.09
     serving
    -0.09
     puzzle
    -0.09
    POSITIVE LOGITS
     slowly
    0.13
     occasionally
    0.12
     rising
    0.11
     varying
    0.11
     tongue
    0.11
     periodically
    0.10
     gradually
    0.10
     increasing
    0.10
     altern
    0.10
     spit
    0.10
    Activations Density 0.009%

    No Known Activations